Catalog Categories Embedding & reranker services

Embedding & reranker services

11 systems in the embedding & reranker services category of the AI Agent Infrastructure Landscape, grouped by maturity tier.

Tier 1 — battle-tested (6)

  • Cohere Embed Hosted embeddings API

    Cohere's hosted embedding models (embed-v3 family) — multi-lingual, image+text, compression. Reranker API (Rerank-v3). Cohere is one of three major LLM startups (alongside Anthropic, OpenAI) by revenue scale.

  • Hugging Face Inference API (Embeddings) HF hosted embeddings

    HF's hosted Inference API and Inference Endpoints — serve any model from the Hub including the BGE/GTE/E5 embedding families.

  • Jina AI Embeddings Open embedding models + API

    Jina AI's embedding family — jina-embeddings-v3 (multilingual), jina-clip-v2 (text+image), jina-colbert-v2. Open-weights + hosted API + ColBERT-style.

  • OpenAI Embeddings OpenAI embedding API

    OpenAI's hosted embedding API — text-embedding-3-small, text-embedding-3-large. Most widely used commercial embedding API in OSS RAG/memory stacks.

  • Sentence Transformers Open embedding training framework

    Reimers & Gurevych's library for training sentence embeddings — substrate under most open-weight embedding models. Now under Hugging Face.

  • Voyage AI (MongoDB) Premium embedding + reranker API

    Specialised embedding and reranker provider — voyage-3, voyage-multilingual, voyage-finance, voyage-law, voyage-code. Acquired by MongoDB Feb 2025 for $220M.

Tier 2 — production-ready (4)

  • BGE (BAAI) BAAI open embedding family

    BAAI (Beijing Academy of AI) BGE family — bge-large/base/small + bge-m3 multilingual + bge-reranker. One of the most widely-used open embedding families.

  • Mistral Embed Mistral embedding API

    Mistral AI's hosted embedding API — mistral-embed; available via Mistral La Plateforme and Azure AI.

  • Mixedbread AI Embedding + reranker API

    Hosted embedding and reranker APIs — mxbai-embed-large + reranker. Open-weight models + paid API + agentic search.

  • Nomic Embed Open embedding + atlas

    Nomic's open-weight embedding models (nomic-embed-text-v1.5, nomic-embed-vision). Nomic Atlas for vector dataset exploration.

Tier 3 — emerging (1)

  • GTE (Alibaba-NLP) Alibaba general text embeddings

    Alibaba DAMO Academy's GTE family — open-weight multilingual embedding models; gte-large/base/small + Qwen-based gte-Qwen2.